Patrimony
The Louis Bachelier Group's patrimony has been defined as all the publications produced by academic researchers thanks to Group funding (ILB, FdR, IEF, Labex) or via the use of EquipEx data (BEDOFIH, EUROFIDAI).
Theoretical study of some statistical procedures applied to complex data.
Bayesian Inference, Compl?tion de matrices, Computational Statistics, Extr?mes spatiaux, Inf?rence bay?sienne, Machine Learning, Matrix Completion, Spatial Extremes, Statistics, Statistiques, Statistiques computationnelle
High dimensional matrix estimation with unknown variance of the noise.
Low rank matrix estimation, Matrix completion, Matrix regression, Recovery of the rank
Matrix completion : statistical and computational aspects.
Apprentissage à grande échelle, Complétion de matrice, High dimension statistics, Large scale optimization, Matrix completion, Statistique en grande dimension
Imputation and low-rank estimation with Missing Not At Random data.
Accelerated proximal gradient method, Denoising, EM algorithm, Informative missing values, Matrix completion, Nuclear norm penalty
Estimation and imputation in Probabilistic Principal Component Analysis with Missing Not At Random data.
Graphical models, Informative missing values, Latent variables, Matrix completion, Missingness graph, Probabilistic principal component analysis, Selection bias
denoiseR: A Package for Low Rank Matrix Estimation.
Bootstrap, Clustering, Correspondence analysis, Count data, Low-rank matrix estimation, Matrix completion, Missing values, SURE, Singular values shrinkage
Imputation and low-rank estimation with Missing Non At Random data.
Accelerated proximal gradient method, Denoising, EM algorithm, Informative missing values, Matrix completion, Nuclear norm penalty